Rough Neuro-Fuzzy Network Applied to Traffic Flow Breakdown in the City of Sao Paulo

In recent years the market behavior has changed, influenced by several aspects like: increased competitiveness, electronic commerce, environment concerns, among others. The new consumption habits have brought products with a shorter life cycle. These behavior increases the amount of discarded and aimlessly items. Predict the traffic behavior could help to make decision about the routing process, as well as enables the improvement in effectiveness and productivity on its physical distribution. This need motivates the search for technological improvements in the Routing performance in metropolitan areas. The purpose of this paper is to present computational evidence that Artificial Neural Network (ANN) could be use to predict the traffic behavior in a metropolitan area such Sao Paulo (around 16 million inhabitants). The proposed methodology involves the application Rough-Fuzzy Sets to define inference morphology for insert the behavior of Dynamic Routing into a structured rule basis, without human expert aid. The attributes of the traffic parameters are described through membership functions. Rough Sets Theory identifies the attributes that are important, and suggest Fuzzy relations to be inserted on a Rough Neuro Fuzzy Network (RNFN) type Multilayer Perceptron (MLP), in order to get an optimal surface response. To measure the performance of the proposed RNFN, the responses of the unreduced rule basis are compared with the reduced rule basis. The results show that by making use of the RNFN, it is possible to reduce the need for human expert in the construction of the Fuzzy inference mechanism in such flow process like traffic breakdown.